1. The Role of Sample Survey Design


 Ralf Damian Hopkins
 1 years ago
 Views:
Transcription
1 Vista's Approach to Sample Survey Design 1978, 1988, 2006, 2007, 2009 Joseph George Caldwell. All Rights Reserved. Posted at Internet website Updated 20 March 2009 (two references added). Contents 1. The Role of Sample Survey Design General Procedures for Development of a Sample Survey Design Development of OMB Clearance Request Package Considerations in the Design of Analytical Surveys Vista's Experience in Sample Survey Design... 8 Selected References in Sample Survey Design The Role of Sample Survey Design Sample survey is concerned with the problem of making inferences about the characteristics of a collection of items  a "population"  based on the characteristics of a portion of the population  a "sample." If the sample is selected from the population in such a way that the probabilities of selection are known, then the theory of statistics may be used to make these inferences, i.e., to estimate population characteristics and to test hypotheses about the population. There are several reasons for employing proper statistical design techniques in a research study. First, the use of statistical sample survey design techniques not only assures sample estimates having satisfactory levels of precision, but it also enables measurement of what that level of precision is. The usual measure of precision is the standard error of the estimate. Second, the use of sound sample survey design procedures improves the ratio of cost to level of precision, by enabling higher precision for a given level of cost, or lower cost for a desired level of precision. The increase in precision or decrease in cost is effected by allocating the sampling effort in ways that take into account the costs of sampling, the variability of the target population, and special features of the target population (such as the occurrence of natural "clusters" of the population, e.g., cities, schools, and households). Third, the use of sound sample survey procedures assures high validity of the estimates, i.e., the estimates will have low bias. A final advantage in the use of statistical design concepts is in enhancing the usefulness of the survey results by assuring (prior to implementation of the survey) that the level of precision of the sample estimates will be sufficient to permit meaningful interpretation. (Note: Precision, or reliability refers to the variability of an estimate  i.e., the extent to which the estimate fluctuates around the average value obtained through repeated sampling. Validity refers to how close this average value (obtained in repeated sampling) is to the "true" (population) value of the parameter being estimated (and also to how well that parameter represents the concept that is desired to be measured). The difference between the average value and the population value is called the bias. Precision is usually measured by the standard error of the estimate. Validity is measured by the bias. Accuracy refers to a combined measure of precision and validity. Accuracy is usually measured by the mean squared error, equal to the square of the standard error plus the square of the bias.)
2 Construction of an efficient survey design is accomplished by taking into account the characteristics of the population being surveyed, the costs of sampling, and the precision requirements of the study. It is important to keep in mind the study requirements, in order to assure that the precision obtained for key variables is sufficient, but not unnecessarily high. Furthermore, it is desirable to obtain comparable levels of precision for estimates of variables that are of comparable importance. The development of a sample design is accomplished by taking into account the identification of the basic estimates of interest together with prior information concerning the variability of the population with respect to the variables of interest and the intercorrelations between these variables. Because most projects have multiple inference objectives, the design is usually not "finetuned" to provide maximum precision for a single estimate. Rather, the design is generally structured to provide acceptable accuracy for a number of relationships of interest. There are two basic types of sample surveys descriptive sample surveys and analytical sample surveys. In a descriptive sample survey, the objective is to obtain estimates of basic descriptive characteristics (such as means or proportions) for the whole population or particular subpopulations of interest. In an analytical sample survey, the primary objective is to be able to estimate the relationship of a particular variable (a "dependent" variable) to other variables (the "independent," or "explanatory," variables): for example, the relationship of client income to program inputs, client characteristics, and regional demographic and economic characteristics. The distinction between a descriptive and an analytical survey has a profound effect on the nature of the survey design. In a descriptive survey, attention usually centers on the estimation of the state of a finite population at some point in time. The estimation objectives of the survey are simple  usually just estimation of means and proportions for the population and various subpopulations, with perhaps some estimation of basic relationships, usually through presentation of results by stratum or by crosstabulations. The sample design process usually proceeds without difficulty  the basic requirement is that the sample size is sufficiently large for all subpopulations of interest. In an analytical survey, on the other hand, attention centers on the estimation of relationships between (dependent and independent) variables, for a conceptually infinite population. Attention centers on making inferences about the process generating or acting on the population, not about the population itself. The purpose of the survey is to develop a model of the process. Usually, a parametric statistical model such as the general linear model (regression model) is used. The analysis involves the iterative steps of model identification, estimation, tests of model adequacy, and respecification. The major differences between an analytical survey and a descriptive survey are the following. In a descriptive survey, we want large sample sizes in subpopulations of interest. In an analytical survey, on the other hand, we want variation and balance in the explanatory variables, and orthogonality (low correlation) between variables that are not causally related. In addition, the finite population correction factor is irrelevant in an analytical survey. This fact can have a substantial impact on sample size determination. A sample survey that has the estimation of relationships as its primary objective differs from the majority of sample surveys, whose objective is simply to compute descriptive statistics (such as percentages) about the populations and subpopulations under study. The relationships between the study variables are often complex, and there are numerous instances in which the independent variables may be correlated to a substantial degree. In some instances, the relationship of the 2
3 correlated independent variables to a dependent variable may be quite difficult to assess. In order to obtain a good estimate of these relationships, the sample design must be structured to "orthogonalize" these "confounded" independent variables, i.e., to reduce the correlation between them. We shall now describe a general procedure for determining a sample design. This description is in two parts. First, we discuss general procedures that apply to both descriptive and analytical survey design. That discussion is followed by a discussion of additional considerations that apply to the development of an analytical survey design. 2. General Procedures for Development of a Sample Survey Design A standardized procedure for developing a sample design is presented below. This general procedure may be followed in developing the sample design for most applications. 1. Specify population of interest The Elements of Survey Design 2. Specify units of analysis and estimates of interest 3. Specify precision objectives of the survey; resource constraints; political constraints 4. Specify other variables of interest (explanatory variables, stratification variables) 5. Review population characteristics (distributional, cost) 6. Develop instrumentation (development, pretest, pilot test, reliability and validity analysis) 7. Develop sample design 8. Determine sample size and allocation 9. Specify sample selection procedure 10. Specify field procedures 11. Determine data processing procedures 12. Develop data analysis plan 13. Outline final report The paragraphs that follow describe each of the steps listed above. 1. Specify Population of Interest The population about which it is desired to make inferences is called the target population. It is defined by four quantities  content, units, extent, and time. (For 3
4 example, we may be interested in estimating the income, of US citizens, residing overseas, in the past year.) In many surveys, there are several different units of analysis (e.g., hospitals and patients, or schools and students). The survey population is a subset of the target population, that recognizes practical constraints, such as inaccessibility or lack of data, cost, and political or legal constraints. Prior to development of a good sample design, it is helpful to summarize what information is known about the survey population, such as means and variances of the population and subpopulations of interest; sampling cost information; and the cluster structure of the population. 2. Define Estimates of Interest The variables that are of interest must be identified (e.g., age, race, sex, earnings, status). The design effort should specify subpopulations that are of interest (e.g., women, the unemployed). Surrogate variables must be identified if desired variables cannot be obtained (e.g., earnings vs. income). The method of observation (record scan, personal interview, telephone interview, or mail questionnaire) must be identified, as must the measures of interest (e.g., mean earnings change in the past year). 3. Specify Objectives and Constraints The precision objectives of the survey may be specified in terms of standard errors or in terms of confidence intervals on key parameter estimates, for highinterest populations. Resource constraints, political and legal constraints, and data measurement constraints must be identified. 4. Specify Other Variables of Interest Variables which can be used to stratify (categorize) the population should be identified. Stratification can be used to improve precision, to reduce costs, to assure adequate precision for subpopulations of interest, and to enable measurement of precision. Also, explanatory variables that can be used in crosstabulations, ratio and regression estimates, and nonresponse analysis should be specified. 5. Review Population Characteristics Whatever information is available on distributional breakdowns (frequency distributions, crosstabulations) should be reviewed. This information can suggest what stratifications might be of value in the design stage. Information on withinstratum variances and intracluster correlation coefficients can also assist the design effort, as can information on sampling costs. 6. Develop Instrumentation The major steps in developing the survey instrumentation are: o Determination of the type of instrumentation o Development of the instruments o Pretest of the instruments o Pilot test of the instruments In developing the survey instruments, a number of factors should be kept in mind. These factors are as follows: o Question content o Question order o Question wording o Question structure/format (open or closed, number of categories) o Questionnaire length 4
5 o Questionnaire layout o Questionnaire instructions o Opportunities for interviewer comment on validity of response 7. Develop Sample Design The process of determining the specific sample design is a creative one. The variety of choice is essentially limitless, and the number of design objectives are usually multiple and conflicting. The recommended procedure is to synthesize several design alternatives which emphasize different design objectives, to characterize the alternatives in terms of precision, cost, and operational problems, and to achieve a consensus on the best overall design. The design alternatives include various combinations of stratification, clustering, multistage sampling, and double sampling. 8. Determine Sample Size and Allocation This step involves specification of items such as the number of firststage and secondstage sample units, the number of sample units per stratum, and the proportion of the panel to be replaced in panel sampling. 9. Specify Sample Selection Procedures It must be decided how the sample units are to be selected  with or without replacement, probabilityproportionaltosize sampling, systematic sampling, RaoHartleyCochran sampling, or controlled selection. 10. Specify Field Procedures "Field procedures" include the number and spacing of questionnaire waves, nature of the initial contact, recall procedures, field edit procedures, and transmittal to central headquarters. 11. Specify Data Processing Procedures "Data processing procedures" include procedures for logging, manual edit, coding, keying, machine edit, data base design, treatment of nonresponse and missing values, and data base documentation. 12. Develop Data Analysis Plan The data analysis plan should include consideration of a preliminary descriptive analysis of the data, nonresponse counts, and treatment of nonresponse. The directed analysis of the data includes computation of estimates of interest, crosstabs, and tests of hypotheses. In an analytical survey, the iterative process of model building must be specified. 13. Report Preparation The report of the analysis should include estimates, tables, charts, commentary, and interpretation. Also, the report may contain tables of generalized variances, a characterization of nonresponse, and discussion of possible sources of bias. 3. Development of OMB Clearance Request Package For US survey efforts requiring collection of data from more than nine individuals or organizations, clearance must be obtained from the Office of Management and Budget (OMB). This clearance is required by the Federal Reports Act; the clearance request is effected by submission of Standard Form 83, "Clearance Request and Notice of Action." If a pretest is conducted involving more than nine respondents, it must also be approved by OMB. Vista staff are very familiar with the procedures required to OMB clearance. We have developed a procedure that has proved effective in obtaining OMB clearance without incurring additional delays. While OMB clearance was formerly accomplished in about six weeks, this process now takes up to four months, with additional time often required by the requesting agency's own review (although the survey 5
6 contractor customarily prepares the justification package, it is the agency that actually submits it to OMB). Vista staff have prepared clearance requests that have "passed" OMB review without a single provision or requirement! We are able to assure smooth accomplishment of the clearance process by adherence to a number of steps, which include: 1. Careful development of the survey instruments, including consideration of item and instrument reliability and validity (with special attention to layout or forms design, and to question content, wording, and order); compatibility of answer categories with traditional government response categories; inclusion of only those data elements required to satisfy the survey objectives; and capitalization on experience with similar questions / instruments in earlier surveys. 2. Careful development of the survey sample design, with full consideration of objectives, sampling costs, and the nature of the target population in developing an efficient sample design. 3. Meticulous attention to the Instructions for Requesting OMB Approval under the Federal Reports Act," as revised. Figure 1 contains a list of the items required in the approval application. 4. Consideration of the terms of relevant legislation, such as the Privacy Act of 1974, the Freedom of Information Act, the Department of Commerce's "Directives for the Conduct of Federal Statistical Activities," and agency regulations in developing the survey instruments and procedures. 5. Close coordination with agency staff, OMB liaison staff, agency counsel, OMB clearance officials, and other government officials before submission of the clearance request form. 6. Consultation with appropriate interested parties. A key item in most surveys is item 5(c), "Consultation with State Government Officials." This consultation is required. Failure to consider the interests and concerns of interested organizations (advocacy groups, professional associations, interstate commissions) can cause serious delays even total failure  in largescale survey efforts. By following the above guidelines, we anticipate no problems in obtaining OMB approval of the survey instruments and design. In essence, our approach consists in capitalizing on previous experience in this area. A key resource in the preparation of the designrelated portions of the qualification statement is the fact that one of the principals of Vista (Dr. Caldwell) is a Ph.D. statistician with over ten years experience in sample survey design. Survey Design Report A final survey design report generally includes revised pretested instrument, a recommended sample design (including a description of the sample selection procedure and the probabilities of selection for the sample units), and an OMB clearance request package. The instruments and OMB package are included as appendices. 4. Considerations in the Design of Analytical Surveys As mentioned earlier, the purpose of an analytical study is essentially to develop a model that will describe the relationship of one variable (the dependent variable) to a number of other 6
7 (independent or explanatory) variables. In order to be successful in this objective, we need to include in the model all variables that are expected to have a substantial impact on the dependent variable. The list of potential variables that could reasonably be included in the model may be long. In order to be able to develop a model that adequately describes the relationship of a dependent variable to various independent variables, it is necessary that the independent variables exhibit two basic properties: 1. There is good "balance"  that is, adequate variation  in the independent variables (i.e., there are comparable numbers of "high" and "low" values of each independent variable); and 2. There is a high degree of orthogonality between independent variables that are not causally related. The problem that arises in the development of an analytical survey design (i.e., a survey design to support development of an analytical model) is that there are usually several independent variables of interest, each represented by several levels, and the total combination of levels of variables (or "cells") is usually far larger than the allowed sample size. The standard sampling approach of multiple stratification hence cannot be applied (since the number of stratum "cells" will exceed the sample size). An approach that has often been used in the past in this situation is to select a "judgment" sample of observations. This has a serious drawback, however, in that the theory of statistics can no longer be applied to make inferences from the sample data. Moreover, judgment sampling may easily be avoided, since there is a statistical procedure for sample selection that possesses all of the flexibility of judgment sampling, but has none of the associated drawbacks. This procedure is called controlled selection. A final note concerning the sample selection concerns ways in which prior information on dependent variables or surrogate dependent variables (i.e., manpower levels) can be used in the sample selection process. In "descriptive" surveys, this kind of information is often used as a basis for stratification. In "analytical" surveys, this kind of information is usually not used  the design generally centers on the independent variables, not on the dependent variables. For analytical surveys, we generally utilize the statistical sampling procedure of controlled selection as the basis for the sample design. This procedure was developed for the situation in which multiple stratification results in a number of cells that exceeds the allowable sample size. The procedure is illustrated in Figure 4. In this example, there are a total of three variables of stratification. Two of the variables have three levels, and one of the variables has two levels. There are a total of 3 x 3 x 2 = 18 cells in the multiple stratification, but three of the cells contain no population elements. It is desired to select a sample of n=10 units from the 15 occupied cells of the table. The way that this is done is to specify two "sample patterns," either one of which is satisfactory from an analysis point of view (i.e., has adequate variation and balance in each variable, and adequate orthogonality between the variables), and all of which "cover" the entire crossstratification grid table (i.e., each cell is contained in at least one pattern). Probabilities of selection are then specified for each pattern, and one of the patterns is selected. The selected pattern is the sample to be used. Since every sample pattern was specified such that it was "desirable" from an 7
8 analysis point of view, the sample pattern that is selected is guaranteed to be completely acceptable. Since every unit was contained in at least one pattern, every unit has a nonzero probability of selection, and probability theory can hence be used to support analysis of the data. We see then, that controlled selection possesses all of the advantages of judgment sampling (i.e., every pattern is a "judgment" sample, and exhibits the desired variation in the variables), but none of the disadvantages (selection biases, inability to apply statistical inference to a nonprobability sample). The design task is concerned with determining exactly which variables are to be included in the sample design, and the number of categories of each variable. Specification of the Regression Model An analytical survey is generally concerned with using the sample survey data to estimate the parameters of a linear regression model, such as a multiple regression model. The general form of a regression model is: where y = b 0 + b 1 x 1 + b 2 x b m x m + e y = dependent variable x = independent variable, or explanatory variable b = regression coefficient (model parameter), to be estimated in the regression analysis e = model error term, representing random variations in the dependent variable that are not explained by the rest of the model In regression analysis, there are generally two approaches. One is to attempt to develop a single "combined" regression model that represents the relationship for all members of the population. The other is to break the population into a number of different categories, and to develop a different model for each category. This latter approach (the "separate regressions" approach) is used if the nature of the relationship is quite different for the different categories. If the total number of observations in this analysis is probably not very great, it is prudent to avoid the use of separate regressions, since the precision of the coefficient estimates would generally be unsatisfactorily low. Differences in the nature of the relationship among different categories is generally treated by including "interaction" terms in the model. 5. Vista's Experience in Sample Survey Design Sample surveys that Vista staff have designed include thefollowing: o The 1976 Survey of Institutionalized Persons 8
9 o Survey of the Impact of National Health Insurance on Bureau of Community Health Service Users o Nationwide Hospital Cost Data Study o Professional Services Review Organization (PSRO) Data Base Development Study o Followup Study of Vocational Rehabilitation Clients o Elementary and Secondary School Civil Rights Survey o Needs Assessment of State Social Services Programs o Survey of Discrimination in US Sales and Rental Markets o Survey to Collect Data for the US Highway Capacity Manual o Survey of Coffee Production in Haiti The Hospital Cost Data Study, the PSRO Data Base Development Study, the Housing Market Discrimination Study, and the US Highway Capacity Manual Study involved the development of analytical survey design; the others involved descriptive survey design. In addition to the above onetime sample surveys, Vista staff developed the sampling manuals used by states to collect data for the Social Services Reporting Requirements, for Utilization Review of Medicaid, and for Office of Child Support Enforcement Reporting Requirements. In addition to experience in the design of sample surveys, Vista has capabilities in technical training in the area of sample survey design and analysis. Dr. J. G. Caldwell developed the popular seminar, "Sample Survey Design and Analysis," which has been attended by members of government and industry. A copy of a flyer advertising this seminar is included at the end of this section. Selected References in Sample Survey Design 1. Cochran, W. G., Sampling Techniques, 3rd edition, Wiley, Kish, L., Survey Sampling, Wiley, Des Raj, The Design of Sample Surveys, McGraw Hill, Caldwell, Joseph George, Sample Survey Design and Analysis: A Comprehensive ThreeDay Course with Application to Monitoring and Evaluation. Course developed and presented in 1979 and later years. Course Notes posted at Internet website and 9
10 5. Caldwell, Joseph George, Vista s Approach to Evaluation, or 6. Caldwell, Joseph George, Sample Survey Design for Evaluation, or 10
11 11
12 12
CHAPTER VI RESEARCH METHODOLOGY
CHAPTER VI RESEARCH METHODOLOGY 6.1 Research Design Research is an organized, systematic, data based, critical, objective, scientific inquiry or investigation into a specific problem, undertaken with the
More informationChapter 5: Field experimental designs in agriculture
Chapter 5: Field experimental designs in agriculture Jose Crossa Biometrics and Statistics Unit Crop Research Informatics Lab (CRIL) CIMMYT. Int. Apdo. Postal 6641, 06600 Mexico, DF, Mexico Introduction
More informationNonresponse Adjustment Methodology for NHISMedicare Linked Data
Nonresponse Adjustment Methodology for NHISMedicare Linked Data Michael D. Larsen 1, Michelle Roozeboom 2, and Kathy Schneider 2 1 Department of Statistics, The George Washington University, Rockville,
More informationSurvey Research Methodology
Survey Research Methodology Prepared by: Praveen Sapkota IAAS, TU, Rampur Chitwan, Nepal Social research Meaning of social research A social research is a systematic method of exploring, analyzing and
More informationStrategic Sampling for Better Research Practice Survey Peer Network November 18, 2011
Strategic Sampling for Better Research Practice Survey Peer Network November 18, 2011 Thomas Lindsay, CLA Survey Services John Kellogg, Office of Institutional Research Tom Dohm, Office for Measurement
More informationThe Impact of Relative Standards on the Propensity to Disclose. Alessandro Acquisti, Leslie K. John, George Loewenstein WEB APPENDIX
The Impact of Relative Standards on the Propensity to Disclose Alessandro Acquisti, Leslie K. John, George Loewenstein WEB APPENDIX 2 Web Appendix A: Panel data estimation approach As noted in the main
More informationBIOSTATISTICAL METHODS
BIOSTATISTICAL METHODS FOR TRANSLATIONAL & CLINICAL RESEARCH PROPENSITY SCORE Confounding Definition: A situation in which the effect or association between an exposure (a predictor or risk factor) and
More informationExperimental Study of Graphic Cigarette Warning Labels
December 2010 Experimental Study of Graphic Cigarette Warning Labels Final Results Report Contract No. HHSF223200910135G Task Order 7 Prepared for Center for Tobacco Products Food and Drug Administration
More informationYou can t fix by analysis what you bungled by design. Fancy analysis can t fix a poorly designed study.
You can t fix by analysis what you bungled by design. Light, Singer and Willett Or, not as catchy but perhaps more accurate: Fancy analysis can t fix a poorly designed study. Producing Data The Role of
More informationVocabulary. Bias. Blinding. Block. Cluster sample
Bias Blinding Block Census Cluster sample Confounding Control group Convenience sample Designs Experiment Experimental units Factor Level Any systematic failure of a sampling method to represent its population
More informationMethodology for NonRandomized Clinical Trials: Propensity Score Analysis Dan Conroy, Ph.D., inventiv Health, Burlington, MA
PharmaSUG 2014  Paper SP08 Methodology for NonRandomized Clinical Trials: Propensity Score Analysis Dan Conroy, Ph.D., inventiv Health, Burlington, MA ABSTRACT Randomized clinical trials serve as the
More informationUnit 1 Exploring and Understanding Data
Unit 1 Exploring and Understanding Data Area Principle Bar Chart Boxplot Conditional Distribution Dotplot Empirical Rule Five Number Summary Frequency Distribution Frequency Polygon Histogram Interquartile
More informationLecture Outline. Biost 590: Statistical Consulting. Stages of Scientific Studies. Scientific Method
Biost 590: Statistical Consulting Statistical Classification of Scientific Studies; Approach to Consulting Lecture Outline Statistical Classification of Scientific Studies Statistical Tasks Approach to
More informationChapter 3. Producing Data
Chapter 3. Producing Data Introduction Mostly data are collected for a specific purpose of answering certain questions. For example, Is smoking related to lung cancer? Is use of handheld cell phones associated
More informationThe RegressionDiscontinuity Design
Page 1 of 10 Home» Design» QuasiExperimental Design» The RegressionDiscontinuity Design The regressiondiscontinuity design. What a terrible name! In everyday language both parts of the term have connotations
More informationStrategic Planning for HIV/AIDS
ASAP Regional Training on Epidemiological and Economic Tools for HIV/AIDS Strategic Planning S P Strategic Planning for HIV/AIDS M1S2 Module 1, Session 2 Resultsbased Strategic Planning S P The Strategy
More informationIAASB Main Agenda (February 2007) Page Agenda Item PROPOSED INTERNATIONAL STANDARD ON AUDITING 530 (REDRAFTED)
IAASB Main Agenda (February 2007) Page 2007 423 Agenda Item 6A PROPOSED INTERNATIONAL STANDARD ON AUDITING 530 (REDRAFTED) AUDIT SAMPLING AND OTHER MEANS OF TESTING CONTENTS Paragraph Introduction Scope
More informationGlossary From Running Randomized Evaluations: A Practical Guide, by Rachel Glennerster and Kudzai Takavarasha
Glossary From Running Randomized Evaluations: A Practical Guide, by Rachel Glennerster and Kudzai Takavarasha attrition: When data are missing because we are unable to measure the outcomes of some of the
More informationRequest for Proposals
Request for Proposals Innovative Model for Bringing Autism Expertise and Services to Rural Areas of Pennsylvania The Pennsylvania Department of Public Welfare (DPW) through the Tuscarora Intermediate Unit
More informationSAMPLING ERROI~ IN THE INTEGRATED sysrem FOR SURVEY ANALYSIS (ISSA)
SAMPLING ERROI~ IN THE INTEGRATED sysrem FOR SURVEY ANALYSIS (ISSA) Guillermo Rojas, Alfredo Aliaga, Macro International 8850 Stanford Boulevard Suite 4000, Columbia, MD 21045 IINTRODUCTION. This paper
More informationSOUTH DAKOTA BOARD OF REGENTS. Policy Manual
SUBJECT: Drug Free Environment NUMBER: 4:27 SOUTH DAKOTA BOARD OF REGENTS Policy Manual Drug Free Workplace Policy The South Dakota Board of Regents is committed to providing a drug free workplace. Additional
More informationAP Statistics Exam Review: Strand 2: Sampling and Experimentation Date:
AP Statistics NAME: Exam Review: Strand 2: Sampling and Experimentation Date: Block: II. Sampling and Experimentation: Planning and conducting a study (10%15%) Data must be collected according to a welldeveloped
More informationMDCH IRB REVIEW APPLICATION Authority: Code of Federal Regulations Title 45 Part 46
The Michigan Department of Community Health Institutional Review Board for the Protection of Human Research Subjects Capitol View Building, 7 th Floor, 201 Townsend Street, Lansing, MI 48913 Phone: 517/2411928
More informationDEPARTMENT OF EPIDEMIOLOGY 2. BASIC CONCEPTS
DEPARTMENT OF EPIDEMIOLOGY EXIT COMPETENCIES FOR MPH GRADUATES IN GENERAL EPIDEMIOLOGY 1. DEFINITION AND HISTORICAL PERSPECTIVES 1. Historical Trends in the most common causes of death in the United States.
More informationCHAPTER 3 RESEARCH METHODOLOGY
CHAPTER 3 RESEARCH METHODOLOGY 3.1 Introduction 3.1 Methodology 3.1.1 Research Design 3.1. Research Framework Design 3.1.3 Research Instrument 3.1.4 Validity of Questionnaire 3.1.5 Statistical Measurement
More informationInternational Standard on Auditing (UK) 530
Standard Audit and Assurance Financial Reporting Council June 2016 International Standard on Auditing (UK) 530 Audit Sampling The FRC s mission is to promote transparency and integrity in business. The
More informationUN Handbook Ch. 7 'Managing sources of nonsampling error': recommendations on response rates
JOINT EU/OECD WORKSHOP ON RECENT DEVELOPMENTS IN BUSINESS AND CONSUMER SURVEYS Methodological session II: Task Force & UN Handbook on conduct of surveys response rates, weighting and accuracy UN Handbook
More informationIAASB Main Agenda (September 2005) Page Agenda Item. Analysis of ISA 330 and Mapping Document
IAASB Main Agenda (September 2005 Page 2005 1869 Agenda Item 4D.1 Analysis of ISA 330 and Mapping Document 1. Exhibit 1 sets out statements in ISA 330 that use the present tense to describe auditor actions,
More informationMN 400: Research Methods. PART II The Design of Research
MN 400: Research Methods PART II The Design of Research 1 MN 400: Research Methods CHAPTER 6 Research Design 2 What is Research Design? A plan for selecting the sources and types of information used to
More informationPOLICIES GOVERNING PROCEDURES FOR THE USE OF ANIMALS IN RESEARCH AND TEACHING AT WESTERN WASHINGTON UNIVERSITY and REVIEW OF HUMAN SUBJECT RESEARCH
Appendix 9 POLICIES GOVERNING PROCEDURES FOR THE USE OF ANIMALS IN RESEARCH AND TEACHING AT WESTERN WASHINGTON UNIVERSITY and REVIEW OF HUMAN SUBJECT RESEARCH INTRODUCTION It is the policy of Western Washington
More informationAssurance Engagements Other than Audits or Review of Historical Financial Statements
Issued December 2007 International Standard on Assurance Engagements Assurance Engagements Other than Audits or Review of Historical Financial Statements The Malaysian Institute Of Certified Public Accountants
More informationChapter2 RESEARCH DESIGN
Chapter2 RESEARCH DESIGN 33 2.1 Introduction to Research Methodology: The general meaning of research is the search for knowledge. Research is also defined as a careful investigation or inquiry, especially
More informationChapter 4 DESIGN OF EXPERIMENTS
Chapter 4 DESIGN OF EXPERIMENTS 4.1 STRATEGY OF EXPERIMENTATION Experimentation is an integral part of any human investigation, be it engineering, agriculture, medicine or industry. An experiment can be
More informationINTERNATIONAL STANDARD ON ASSURANCE ENGAGEMENTS 3000 ASSURANCE ENGAGEMENTS OTHER THAN AUDITS OR REVIEWS OF HISTORICAL FINANCIAL INFORMATION CONTENTS
INTERNATIONAL STANDARD ON ASSURANCE ENGAGEMENTS 3000 ASSURANCE ENGAGEMENTS OTHER THAN AUDITS OR REVIEWS OF HISTORICAL FINANCIAL INFORMATION (Effective for assurance reports dated on or after January 1,
More informationLecture 2. Key Concepts in Clinical Research
Lecture 2 Key Concepts in Clinical Research Outline Key Statistical Concepts Bias and Variability Type I Error and Power Confounding and Interaction Statistical Difference vs Clinical Difference Onesided
More informationParent/Student Rights in Identification, Evaluation, and Placement
Parent/Student Rights in Identification, Evaluation, and Placement The following is a description of the rights granted to students with a disability by Section 504 of the Rehabilitation Act of 1973, a
More informationI. Survey Methodology
I. Survey Methodology The Elon University Poll is conducted using a stratified random sample of households with telephones in the population of interest in this case, citizens in North Carolina. The sample
More informationCARE Crossproject Collectives Analysis: Technical Appendix
CARE Crossproject Collectives Analysis: Technical Appendix The CARE approach to development support and women s economic empowerment is often based on the building blocks of collectives. Some of these
More informationTHE USE OF MULTIVARIATE ANALYSIS IN DEVELOPMENT THEORY: A CRITIQUE OF THE APPROACH ADOPTED BY ADELMAN AND MORRIS A. C. RAYNER
THE USE OF MULTIVARIATE ANALYSIS IN DEVELOPMENT THEORY: A CRITIQUE OF THE APPROACH ADOPTED BY ADELMAN AND MORRIS A. C. RAYNER Introduction, 639. Factor analysis, 639. Discriminant analysis, 644. INTRODUCTION
More informationREVISED CODEX GENERAL STANDARD FOR IRRADIATED FOODS CODEX STAN , REV
Irradiated foods Page 1 of 10 1. SCOPE REVISED CODEX GENERAL STANDARD FOR IRRADIATED FOODS CODEX STAN 1061983, REV.12003 This standard applies to foods processed by ionizing radiation that is used in
More informationPLS 506 Mark T. Imperial, Ph.D. Lecture Notes: Reliability & Validity
PLS 506 Mark T. Imperial, Ph.D. Lecture Notes: Reliability & Validity Measurement & Variables  Initial step is to conceptualize and clarify the concepts embedded in a hypothesis or research question with
More informationStrategies to Develop Food Frequency Questionnaire
Strategies to Develop Food Frequency www.makrocare.com Food choices are one of the health related behaviors that are culturally determined. Public health experts and nutritionists have recognized the influence
More informationLecture Slides. Elementary Statistics Eleventh Edition. by Mario F. Triola. and the Triola Statistics Series 1.11
Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by Mario F. Triola 1.11 Chapter 1 Introduction to Statistics 11 Review and Preview 12 Statistical Thinking 13
More informationBiost 590: Statistical Consulting
Biost 590: Statistical Consulting Statistical Classification of Scientific Questions October 3, 2008 Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics, University of Washington 2000, Scott S. Emerson,
More informationStandards of Conduct for Transmission Providers
Standards of Conduct for Transmission Providers Posted and Effective as of December 30, 2016 Puget Sound Energy ( PSE ) is a public utility that owns, operates, and controls facilities used for the transmission
More informationQuality Digest Daily, March 3, 2014 Manuscript 266. Statistics and SPC. Two things sharing a common name can still be different. Donald J.
Quality Digest Daily, March 3, 2014 Manuscript 266 Statistics and SPC Two things sharing a common name can still be different Donald J. Wheeler Students typically encounter many obstacles while learning
More informationISC GRADE XI HUMANITIES ( ) PSYCHOLOGY. Chapter 2 Methods of Psychology
ISC GRADE XI HUMANITIES (201819) PSYCHOLOGY Chapter 2 Methods of Psychology OUTLINE OF THE CHAPTER (i) Scientific Methods in Psychology observation, case study, surveys, psychological tests, experimentation
More informationBusiness Impact Analysis
ACTION: Final DATE: 05/23/2018 8:24 AM Business Impact Analysis Agency Name: Ohio Department of Medicaid (ODM) Regulation/Package Title: Dental services Rule Number(s): Rule 5160501 with appendices A
More informationPractitioner s Guide To Stratified Random Sampling: Part 1
Practitioner s Guide To Stratified Random Sampling: Part 1 By Brian Kriegler November 30, 2018, 3:53 PM EST This is the first of two articles on stratified random sampling. In the first article, I discuss
More informationChapter 1: Data Collection Pearson Prentice Hall. All rights reserved
Chapter 1: Data Collection 2010 Pearson Prentice Hall. All rights reserved 11 Statistics is the science of collecting, organizing, summarizing, and analyzing information to draw conclusions or answer
More informationTFI WHO 20 Avenue Appia 1211 Geneva 27, Switzerland. Gentlemen:
Donald D. Foreman, Director Federal Government Affairs 1455 Pennsylvania Avenue, NW, Suite 925 Washington, DC 20004 Telephone: (202) 6267200 Fax: (202) 6267208 TFI WHO 20 Avenue Appia 1211 Geneva 27,
More informationFor general queries, contact
Much of the work in Bayesian econometrics has focused on showing the value of Bayesian methods for parametric models (see, for example, Geweke (2005), Koop (2003), Li and Tobias (2011), and Rossi, Allenby,
More informationMethodological Considerations to Minimize Total Survey Error in the National Crime Victimization Survey
Methodological Considerations to Minimize Total Survey Error in the National Crime Victimization Survey Andrew Moore, M.Stat., RTI International Marcus Berzofsky, Dr.P.H., RTI International Lynn Langton,
More informationCommunity Friends THIRD PARTY FUNDRAISING
Community Friends THIRD PARTY FUNDRAISING Thank you for selecting the Breast Cancer Coalition of Rochester as the beneficiary of your fundraising event or activity (mutually referred to as event ). The
More informationLSS Tariff Review Phase 2 Report
LSS Tariff Review Phase 2 Report November 2004 I. EXECUTIVE SUMMARY This report is an interim report on progress during Phase 2 of the Legal Services Society (LSS) Tariff Review, which involved research
More informationClinical Research Scientific Writing. K. A. Koram NMIMR
Clinical Research Scientific Writing K. A. Koram NMIMR Clinical Research Branch of medical science that determines the safety and effectiveness of medications, devices, diagnostic products and treatment
More informationIntroduction: Statistics, Data and Statistical Thinking Part II
Introduction: Statistics, Data and Statistical Thinking Part II FREC/STAT 608 Dr. Tom Ilvento Department of Food and Resource Economics Let s Continue with our introduction We need terms and definitions
More informationMATH134. Experimental Design
Experimental Design Controlled Experiment: Researchers assign treatment and control groups and examine any resulting changes in the response variable. (causeandeffect conclusion) Observational Study:
More informationUse of Standards in Substantial Equivalence Determinations
Guidance for Industry and for FDA Staff Use of Standards in Substantial Equivalence Determinations Document issued on: March 12, 2000 U.S. Department Of Health And Human Services Food and Drug Administration
More informationFamily THE 2002 NATIONAL FAMILY PLANNING PROGRAM EFFORT INDEX FOR ETHIOPIA. ETHIOPIA October 2002
THE 02 NATIONAL PROGRAM EFFORT INDEX FOR ETHIOPIA Produced by ETHIOPIA October 02 Family The Futures Group International In collaboration with: Research Triangle Institute (RTI) Planning The Center for
More informationLecture (chapter 1): Introduction
Lecture (chapter 1): Introduction Ernesto F. L. Amaral January 17, 2018 Advanced Methods of Social Research (SOCI 420) Source: Healey, Joseph F. 2015. Statistics: A Tool for Social Research. Stamford:
More informationMay 16, Division of Dockets Management (HFA305) Food and Drug Administration 5630 Fishers Lane, Room 1061 Rockville, MD 20852
701 Pennsylvania Avenue, NW Suite 800 Washington, D.C. 20004 2654 Tel: 202 783 8700 Fax: 202 783 8750 www.advamed.org May 16, 2014 Division of Dockets Management (HFA305) Food and Drug Administration
More informationSRI LANKA AUDITING STANDARD 530 AUDIT SAMPLING CONTENTS
SRI LANKA AUDITING STANDARD 530 AUDIT SAMPLING (Effective for audits of financial statements for periods beginning on or after 01 January 2014) CONTENTS Paragraph Introduction Scope of this SLAuS... 1
More informationMC IRB Protocol No.:
APPLICATION FORM  INITIAL REVIEW INSTITUTIONAL REVIEW BOARD Room 117 Main Building 555 Broadway Dobbs Ferry NY 10522 Phone: 9146747814 / Fax: 9146747840 / mcirb@mercy.edu MC IRB Protocol No.: Date
More informationWhat s New in SUDAAN 11
What s New in SUDAAN 11 Angela Pitts 1, Michael Witt 1, Gayle Bieler 1 1 RTI International, 3040 Cornwallis Rd, RTP, NC 27709 Abstract SUDAAN 11 is due to be released in 2012. SUDAAN is a statistical software
More informationTesting for nonresponse and sample selection bias in contingent valuation: Analysis of a combination phone/mail survey
Whitehead, J.C., Groothuis, P.A., and Blomquist, G.C. (1993) Testing for Nonresponse and Sample Selection Bias in Contingent Valuation: Analysis of a Combination Phone/Mail Survey, Economics Letters, 41(2):
More informationOREGON PUBLIC UTILITY COMMISSION ANNUAL PERFORMANCE REPORT INTRODUCTION LETTER January 16, 2004
OREGON PUBLIC UTILITY COMMISSION ANNUAL PERFORMANCE REPORT INTRODUCTION LETTER January 16, 2004 Re: Annual Performance Report Oregon Public Utility Commission Following is a summary of Our Performance
More informationDIVISION OF PUBLIC & BEHAVIORAL HEALTH BUREAU OF HEALTH CARE QUALITY AND COMPLIANCE LCB File No. R Informational Statement per NRS 233B.
DIVISION OF PUBLIC & BEHAVIORAL HEALTH BUREAU OF HEALTH CARE QUALITY AND COMPLIANCE LCB File No. R12016 Informational Statement per NRS 233B.066 1. A clear and concise explanation of the need for the
More informationCarrying out an Empirical Project
Carrying out an Empirical Project Empirical Analysis & Style Hint Special program: Pretraining 1 Carrying out an Empirical Project 1. Posing a Question 2. Literature Review 3. Data Collection 4. Econometric
More information2016 Social Service Funding Application NonAlcohol Funds
2016 Social Service Funding Application NonAlcohol Funds Applications for 2016 funding must be complete and submitted electronically to the City Manager s Office at ctoomay@lawrenceks.org by 5:00 pm on
More informationChapter 1 Data Collection
Chapter 1 Data Collection OUTLINE 1.1 Introduction to the Practice of Statistics 1.2 Observational Studies versus Designed Experiments 1.3 Simple Random Sampling 1.4 Other Effective Sampling Methods 1.5
More informationPublic Health Masters (MPH) Competencies and Coursework by Major
I. Master of Science of Public Health A. Core Competencies B. Major Specific Competencies i. Professional Health Education ii. iii. iv. Family Activity Physical Activity Behavioral, Social, and Community
More informationData collection, summarizing data (organization and analysis of data) The drawing of inferences about a population from a sample taken from
1 Nature of Statistics The Study of statistics involves; Data collection, summarizing data (organization and analysis of data) and interpretation of data. The drawing of inferences about a population from
More information980 North Jefferson Street, Jacksonville, Florida T TDD Toll Free
This document discusses the North Florida Transportation Planning Organization s approach to meeting the needs of persons with limited English Proficiency in executing the TPO s transportation planning
More informationRef: E 007. PGEU Response. Consultation on measures for improving the recognition of medical prescriptions issued in another Member State
Ref:11.11.24E 007 PGEU Response Consultation on measures for improving the recognition of medical prescriptions issued in another Member State PGEU The Pharmaceutical Group of the European Union (PGEU)
More informationTitle: A robustness study of parametric and nonparametric tests in ModelBased Multifactor Dimensionality Reduction for epistasis detection
Author's response to reviews Title: A robustness study of parametric and nonparametric tests in ModelBased Multifactor Dimensionality Reduction for epistasis detection Authors: Jestinah M Mahachie John
More informationBiostatistics for Med Students. Lecture 1
Biostatistics for Med Students Lecture 1 John J. Chen, Ph.D. Professor & Director of Biostatistics Core UH JABSOM JABSOM MD7 February 14, 2018 Lecture note: http://biostat.jabsom.hawaii.edu/education/training.html
More informationISPM No. 9 GUIDELINES FOR PEST ERADICATION PROGRAMMES (1998)
ISPM No. 9 INTERNATIONAL STANDARDS FOR PHYTOSANITARY MEASURES ISPM No. 9 GUIDELINES FOR PEST ERADICATION PROGRAMMES (1998) Produced by the Secretariat of the International Plant Protection Convention FAO
More informationPerformance Improvement Project Implementation & Submission Tool
PLANNING TEMPLATE Performance Improvement Project Implementation & Submission Tool INTRODUCTION & INSTRUCTION This tool provides a structure for development and submission of Performance Improvement Projects
More informationStructural assessment of heritage buildings
Defence Sites 69 Structural assessment of heritage buildings M. Holicky & M. Sykora Klokner Institute, Czech Technical University in Prague, Czech Republic Abstract Reliability assessment of heritage buildings
More informationChapter 4 Review. Name: Class: Date: Multiple Choice Identify the choice that best completes the statement or answers the question.
Name: Class: Date: Chapter 4 Review Multiple Choice Identify the choice that best completes the statement or answers the question. 1. Use Scenario 41. The newspaper asks you to comment on their survey
More informationASSESSING THE EFFECTS OF MISSING DATA. John D. Hutcheson, Jr. and James E. Prather, Georgia State University
ASSESSING THE EFFECTS OF MISSING DATA John D. Hutcheson, Jr. and James E. Prather, Georgia State University Problems resulting from incomplete data occur in almost every type of research, but survey research
More informationAppendix D: Statistical Modeling
Appendix D: Statistical Modeling Cluster analysis Cluster analysis is a method of grouping people based on specific sets of characteristics. Often used in marketing and communication, its goal is to identify
More informationReveal Relationships in Categorical Data
SPSS Categories 15.0 Specifications Reveal Relationships in Categorical Data Unleash the full potential of your data through perceptual mapping, optimal scaling, preference scaling, and dimension reduction
More informationSaville Consulting Wave Professional Styles Handbook
Saville Consulting Wave Professional Styles Handbook PART 4: TECHNICAL Chapter 19: Reliability This manual has been generated electronically. Saville Consulting do not guarantee that it has not been changed
More informationScope of Practice for the Diagnostic Ultrasound Professional
Scope of Practice for the Diagnostic Ultrasound Professional Copyright 19932000 Society of Diagnostic Medical Sonographers, Dallas, Texas USA: All Rights Reserved Worldwide. Organizations which endorse
More informationSALISBURY UNIVERSITY COMMITTEE ON HUMAN RESEARCH APPLICATION FOR RESEARCH INVOLVING HUMAN SUBJECTS
SALISBURY UNIVERSITY COMMITTEE ON HUMAN RESEARCH APPLICATION FOR RESEARCH INVOLVING HUMAN SUBJECTS If you have a full committee review: 1. Your proposal must be submitted at minimum 14 days before the
More informationCh 1.1 & 1.2 Basic Definitions for Statistics
Ch 1.1 & 1.2 Basic Definitions for Statistics Objective A : Basic Definition A1. Definition What is Statistics? Statistics is the science of collecting, organizing, summarizing, and analyzing data to draw
More informationClass II Special Controls Guidance Document: Intraoral Devices for Snoring and/or Obstructive Sleep Apnea; Guidance for Industry and FDA
Class II Special Controls Guidance Document: Intraoral Devices for Snoring and/or Obstructive Sleep Apnea; Guidance for Industry and FDA Document issued on: November 12, 2002 This document supersedes the
More informationA STUDY OF PEACE CORPS DECLINATIONS REPORT ON METHODS
A STUDY OF PEACE CORPS DECLINATIONS REPORT ON METHODS A report of the respondents, instruments, and procedures used in a survey of acceptors and decliners. Prepared for the Peace Corps by David G. Bowers
More informationLecture Outline Biost 517 Applied Biostatistics I
Lecture Outline Biost 517 Applied Biostatistics I Scott S. Emerson, M.D., Ph.D. Professor of Biostatistics University of Washington Lecture 2: Statistical Classification of Scientific Questions Types of
More informationGuidance for Industry
Reprinted from FDA s website by Guidance for Industry E14 Clinical Evaluation of QT/QTc Interval Prolongation and Proarrhythmic Potential for NonAntiarrhythmic Drugs Questions and Answers (R1) U.S. Department
More informationAnalysis A step in the research process that involves describing and then making inferences based on a set of data.
1 Appendix 1:. Definitions of important terms. Additionality The difference between the value of an outcome after the implementation of a policy, and its value in a counterfactual scenario in which the
More informationCrime & Victimisation Module
Standard Report on Methods and Quality for Crime & Victimisation Module This documentation applies to the reporting period: 2015 Last edited 17.10.2016 Central Statistics Office Skehard Road Cork Tel.:
More informationWelcome Module Index Glossary Epiville Chamber of Commerce About this site Requirements. Faculty Highlight: Pam R. FactorLitvak, PhD
 Page 23 45 67  Discussion Question While many consider the ecological study design methodologically inferior to the cohort and case control designs, this exercise will highlight some of its unique strengths
More informationBest on the Left or on the Right in a Likert Scale
Best on the Left or on the Right in a Likert Scale Overview In an informal poll of 150 educated research professionals attending the 2009 Sawtooth Conference, 100% of those who voted raised their hands
More informationPSYCHOMETRIC PROPERTIES OF CLINICAL PERFORMANCE RATINGS
PSYCHOMETRIC PROPERTIES OF CLINICAL PERFORMANCE RATINGS A total of 7931 ratings of 482 third and fourthyear medical students were gathered over twelve fourweek periods. Ratings were made by multiple
More informationChapter 3. Producing Data
Chapter 3 Producing Data Types of data collected Anecdotal data data collected haphazardly (not representative!!) Available data existing data (examples: internet, library, census bureau,.) Gather own
More information